“Big Data for IoT: Analytics from Descriptive to Predictive to Prescriptive” was presented to the Phoenix Data Conference on 11/4/17 at Grand Canyon University.
As the Internet of Things (IoT) floods data lakes and fills data oceans with sensor and real-world data, analytic tools and real-time responsiveness will require improved platforms and applications to deal with the data flow and move from descriptive to predictive to prescriptive analysis and outcomes.
3. See also: Internet of Things Innovations & Megatrends
Presentation to the IEEE Computer Society Phoenix
On December 14, 2016 at http://bit.ly/2hLXjPT
IoT Overview and Ecosystems
IoT Computing Platforms and Sensors
IoT Gateway and Network Connections
IoT Application Arenas
• Consumer and Home Automation
• Wearables
• Healthcare and Life Science
• Retail and Logistics
• Industrial
• Smart Buildings
• Smart Cities and Environment
• Transportation
IoT Security and Privacy
IoT Standards and Organizations
IoT Data Applications and Business Models
Next mega IoT update scheduled for 12/13/17 at DeVry University Phoenix for the
IEEE Computer Society Phoenix (http://ewh.ieee.org/r6/phoenix/compsociety/)
10. Sensor Cluster Trends for Mobile Phones
(Inertial Measurement Units)
AMS AV-MLV-P2 is a volatile organic compounds (VOC) gas sensor which can detect
alcohols, aldehydes, ketones, organic acids, amines, aliphatic and aromatic hydrocarbons.
14. Wi-Fi Ecosystem is Undergoing Change
http://www.wirelessdesignmag.com/article/2016/05/now-80211ac-wave-1-rolled-out-whats-next-wi-fi
15. Why the Present 802.11 Technology is Inadequate:
• Absence of power-saving mechanisms: The energy constraints of sensor networks are not
considered in the current IEEE 802.11 standard.
• Unsuitable bands: Due to their short wireless range and high obstruction losses, existing
Wi-Fi bands require the use of intermediate nodes, adding complexity to the network.
IEEE 802.11ah Requirements to Support M2M Communications:
• Up to 8,191 devices associated with an access point (AP) through a hierarchical identifier
structure
• Carrier frequencies of approximately 900 MHz (license-exempt) that are less congested
and guarantee a long range
• Transmission range up to 1 km in outdoor areas
• Data rates of at least 100 kbps
• One-hop network topologies
• Short and infrequent data transmissions (data packet size approximately 100 bytes and
packet inter-arrival time greater than 30 s)
• Very low energy consumption by adopting power saving strategies
• Cost-effective solution for network device manufacturers
IEEE 802.11ah Wi-Fi Approach for M2M Communications
http://www.ieee802.org/11/Reports/tgah_update.htm
http://www.techrepublic.com/article/802-11ah-wi-fi-protocol-for-iot-solves-two-m2m-problems/
41. Predix delivers the industrial intelligence you need to transform your operations
and generate new revenues. Combining sophisticated asset modeling, big data
processing, analytics, and applications, Predix provides the IT foundation for
tomorrow’s industrial operations. Predix lets you deploy processing and analytics
power to control edge assets in real time or analyze big data in the cloud using
the secure Predix connectivity and execution environment.
https://www.ge.com/digital/predix/
44. https://www.microsoft.com/en-us/cognitive-toolkit/
https://github.com/microsoft/cntk
CNTK can be included as a library in your Python, C#, or C++ programs, or used
as a standalone machine learning tool through its own model description
language (BrainScript). In addition you can use the CNTK model evaluation
functionality from your Java program.
CNTK supports 64-bit Linux or 64-bit Windows operating systems. To install you
can either choose pre-compiled binary packages, or compile the toolkit from the
source provided in GitHub.
59. Google’s Serverless Cloud IoT platform
Google Cloud IoT is a comprehensive set of fully managed and integrated services that
allow you to easily and securely connect, manage, and ingest IoT data from globally
dispersed devices at a large scale, process and analyze/visualize that data in real time, and
implement operational changes and take actions as needed. Device data captured by Cloud
IoT Core gets published to Cloud Pub/Sub for downstream analytics. You can do ad hoc
analysis using Google BigQuery, easily run advanced analytics and apply machine learning
with Cloud Machine Learning Engine, or visualize IoT data results with rich reports and
dashboards in Google Data Studio. https://cloud.google.com/solutions/iot/
60. From Data Warehouses to Data Lakes:
Mission-critical information is quickly moving from databases to data lakes, from
structured to unstructured data and from millions of transactions to billions of
interactions. Qubole can help you transition from a legacy, on-premises data
warehouse to an elastic, open source data lake in the cloud.
https://www.qubole.com/
63. TensorFlow™ is an open source software library for numerical computation using
data flow graphs. Nodes in the graph represent mathematical operations, while
the graph edges represent the multidimensional data arrays (tensors)
communicated between them. The flexible architecture allows you to deploy
computation to one or more CPUs or GPUs in a desktop, server, or mobile device
with a single API. TensorFlow™ was originally developed by researchers and
engineers working on the Google Brain Team within Google's Machine
Intelligence research organization for the purposes of conducting machine
learning and deep neural networks research, but the system is general enough to
be applicable in a wide variety of other domains as well.
TensorFlow™ has APIs available in several languages both for constructing and
executing a TensorFlow graph. The Python API is at present the most complete
and the easiest to use, but other language APIs may be easier to integrate into
projects and may offer some performance advantages in graph execution.
https://www.tensorflow.org/